End of training

README.md

@@ -103,7 +103,7 @@ xformers_attention: null
 
 This model is a fine-tuned version of [Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.4639
+- Loss: 3.4301
 
 ## Model description
 
@@ -138,9 +138,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | 10.0714       | 0.0015 | 1    | 9.6841          |
-| 9.82          | 0.0045 | 3    | 9.2804          |
-| 8.7056        | 0.0089 | 6    | 6.3620          |
-| 4.6051        | 0.0134 | 9    | 3.4639          |
+| 9.8085        | 0.0045 | 3    | 9.2877          |
+| 8.723         | 0.0089 | 6    | 6.3874          |
+| 4.6364        | 0.0134 | 9    | 3.4301          |
 
 
 ### Framework versions

adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "o_proj",
-    "up_proj",
+    "gate_proj",
     "v_proj",
+    "q_proj",
+    "up_proj",
     "down_proj",
-    "gate_proj",
-    "q_proj"
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8582963b961ab25cfb267754037627a3c91f2e29660f0ba89a280e956620689a
+oid sha256:269c09aa69bead95ac748047c531aa8922ee921582f751c5f190bb41b72f5a8a
 size 35313738

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33343daee1ee6a6dc33af650613c9a7aecae25d982b09a8d3967d27eaa324c19
+oid sha256:1a9f301dd1b5c76ad74770099510dea849e9e5512c6cde06b8477a69e2c986eb
 size 35237104

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5235a99abae682b5b1490f6a9df0a8861b8e91f3470797e2fef11dca025dbf7
+oid sha256:8910c913daa72aa2ee1f187619a3777cdd3adf003c43811644b4605775f3d33a
 size 6776